cxl: Wrap iterations over afu slices inside 'afu_list_lock'
PATCH v3 1/1 cxl: Wrap iterations over afu slices inside 'afu_list_lock'
Within cxl module, iteration over array 'adapter->slices' may be racy at few points as it might be simultaneously read during an EEH and its contents being set to NULL while driver is being unloaded or unbound from the adapter. This might result in a NULL pointer to 'struct afu' being de-referenced during an EEH thereby causing a kernel oops.
This patch fixes this by making sure that all access to the array 'adapter->slices' is wrapped within the context of spin-lock 'adapter->afu_list_lock'.
---
Changelog:
v3:
* Updated a slice loop in cxl_pci_error_detectected() to ignore NULL slices [Fred]
* Added a NULL AFU check in cxl_pci_slot_reset() [Fred]
v2:
* Fixed a wrong comparison of non-null pointer [Fred]
* Moved a call to cxl_vphb_error_detected() within a branch that checks for not null AFU pointer in 'adapter->slices' [Fred]
* Removed a misleading comment in code.
--- drivers/misc/cxl/guest.c | 2 ++ drivers/misc/cxl/pci.c | 39 ++++++++++++++++++++++++++++++--------- 2 files changed, 32 insertions(+), 9 deletions(-)
drivers/misc/cxl/guest.c +2 -0
@@ -267,6 +267,7 @@ static int guest_reset(struct cxl *adapter)int i, rc;pr_devel ("Adapter reset request\n" ); +spin_lock (&adapter->afu_list_lock);for (i =0 ; i < adapter->slices; i++) {if ((afu = adapter->afu[i])) { pci_error_handlers(afu, CXL_ERROR_DETECTED_EVENT,
@@ -283,6 +284,7 @@ static int guest_reset(struct cxl *adapter)pci_error_handlers (afu,CXL_RESUME_EVENT ,0 ); } } +spin_unlock (&adapter->afu_list_lock);return rc; }
drivers/misc/cxl/pci.c +30 -9
@@ -1805,7 +1805,7 @@ static pci_ers_result_t cxl_vphb_error_detected(struct cxl_afu *afu,/* There should only be one entry, but go through the list * anyway */ -if (afu->phb ==NULL ) +if (afu ==NULL || afu->phb ==NULL )return result;list_for_each_entry (afu_dev, &afu->phb->bus->devices, bus_list) {
@@ -1832,7 +1832,8 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev, {struct cxl *adapter =pci_get_drvdata (pdev);struct cxl_afu *afu; -pci_ers_result_t result =PCI_ERS_RESULT_NEED_RESET , afu_result; +pci_ers_result_t result =PCI_ERS_RESULT_NEED_RESET ; +pci_ers_result_t afu_result =PCI_ERS_RESULT_NEED_RESET ;int i;/* At this point, we could still have an interrupt pending.
@@ -1843,6 +1844,7 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev,/* If we're permanently dead, give up. */ if (state == pci_channel_io_perm_failure) { +spin_lock (&adapter->afu_list_lock);for (i =0 ; i < adapter->slices; i++) { afu = adapter->afu[i];/*
@@ -1851,6 +1853,7 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev,*/ cxl_vphb_error_detected (afu, state); } +spin_unlock (&adapter->afu_list_lock);return PCI_ERS_RESULT_DISCONNECT ; }
@@ -1932,11 +1935,17 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev,* * In slot_reset, free the old resources and allocate new ones. * * In resume, clear the flag to allow things to start. */ + +/* Make sure no one else changes the afu list */ +spin_lock (&adapter->afu_list_lock); +for (i =0 ; i < adapter->slices; i++) { afu = adapter->afu[i]; - afu_result =cxl_vphb_error_detected (afu, state); +if (afu ==NULL ) +continue ; + afu_result =cxl_vphb_error_detected (afu, state);cxl_context_detach_all (afu); cxl_ops->afu_deactivate_mode (afu, afu->current_mode);pci_deconfigure_afu (afu);
@@ -1948,6 +1957,7 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev, (result == PCI_ERS_RESULT_NEED_RESET)) result =PCI_ERS_RESULT_NONE ; } +spin_unlock (&adapter->afu_list_lock);/* should take the context lock here */ if (cxl_adapter_context_lock (adapter) !=0 )
@@ -1980,14 +1990,18 @@ static pci_ers_result_t cxl_pci_slot_reset(struct pci_dev *pdev)*/ cxl_adapter_context_unlock (adapter); +spin_lock (&adapter->afu_list_lock);for (i =0 ; i < adapter->slices; i++) { afu = adapter->afu[i]; +if (afu ==NULL ) +continue ; +if (pci_configure_afu (afu, adapter, pdev)) - goto err; + goto err_unlock;if (cxl_afu_select_best_mode (afu)) - goto err; + goto err_unlock;if (afu->phb ==NULL )continue ;
@@ -1999,16 +2013,16 @@ static pci_ers_result_t cxl_pci_slot_reset(struct pci_dev *pdev) ctx =cxl_get_context (afu_dev);if (ctx &&cxl_release_context (ctx)) - goto err; + goto err_unlock; ctx =cxl_dev_context_init (afu_dev);if (IS_ERR (ctx)) - goto err; + goto err_unlock; afu_dev->dev.archdata.cxl_ctx = ctx;if (cxl_ops->afu_check_and_enable (afu)) - goto err; + goto err_unlock; afu_dev->error_state = pci_channel_io_normal;
@@ -2029,8 +2043,13 @@ static pci_ers_result_t cxl_pci_slot_reset(struct pci_dev *pdev) result =PCI_ERS_RESULT_DISCONNECT ; } } + +spin_unlock (&adapter->afu_list_lock);return result; +err_unlock: +spin_unlock (&adapter->afu_list_lock); + err:/* All the bits that happen in both error_detected and cxl_remove * should be idempotent, so we don't need to worry about leaving a mix
@@ -2051,10 +2070,11 @@ static void cxl_pci_resume(struct pci_dev *pdev)* This is not the place to be checking if everything came back up * properly, because there's no return value: do that in slot_reset. */ +spin_lock (&adapter->afu_list_lock);for (i =0 ; i < adapter->slices; i++) { afu = adapter->afu[i]; -if (afu->phb ==NULL ) +if (afu ==NULL || afu->phb ==NULL )continue ;list_for_each_entry (afu_dev, &afu->phb->bus->devices, bus_list) {
@@ -2063,6 +2083,7 @@ static void cxl_pci_resume(struct pci_dev *pdev) afu_dev->driver->err_handler->resume (afu_dev); } } +spin_unlock (&adapter->afu_list_lock); }static const struct pci_error_handlers cxl_err_handler = {
Signature · 1 line
2.20.1
Quoted 1 line · Vaibhav Jain
Within cxl module, iteration over array '
adapter->slices' may be racy
adapter->slices isn't an array, adapter->afu is the array.
Quoted 10 lines
at few points as it might be simultaneously read during an EEH and its contents being set to NULL while driver is being unloaded or unbound from the adapter. This might result in a NULL pointer to 'struct afu' being de-referenced during an EEH thereby causing a kernel oops.
This patch fixes this by making sure that all access to the array '
adapter->slices' is wrapped within the context of spin-lock 'adapter->afu_list_lock'.Signed-off-by Vaibhav Jain <[email protected]>
Does this need to go to stable? (I'm guessing we've been hitting actual Oopses?)
Quoted 181 lines
---
Changelog:v3:
* Updated a slice loop incxl_pci_error_detectected()to ignore NULL slices [Fred]
* Added a NULL AFU check incxl_pci_slot_reset()[Fred]v2:
* Fixed a wrong comparison of non-null pointer [Fred]
* Moved a call tocxl_vphb_error_detected()within a branch that checks for not null AFU pointer in 'adapter->slices' [Fred]
* Removed a misleading comment in code.--- drivers/misc/cxl/guest.c | 2 ++ drivers/misc/cxl/pci.c | 39 ++++++++++++++++++++++++++++++--------- 2 files changed, 32 insertions(+), 9 deletions(-)drivers/misc/cxl/guest.c +2
-0@@ -267,6 +267,7 @@ static int guest_reset(struct cxl *adapter)int i, rc;pr_devel ("Adapter reset request\n" ); +spin_lock (&adapter->afu_list_lock);for (i =0 ; i < adapter->slices; i++) {if ((afu = adapter->afu[i])) { pci_error_handlers(afu, CXL_ERROR_DETECTED_EVENT,@@ -283,6 +284,7 @@ static int guest_reset(struct cxl *adapter)pci_error_handlers (afu,CXL_RESUME_EVENT ,0 ); } } +spin_unlock (&adapter->afu_list_lock);return rc; }drivers/misc/cxl/pci.c +30
-9@@ -1805,7 +1805,7 @@ static pci_ers_result_t cxl_vphb_error_detected(struct cxl_afu *afu,/* There should only be one entry, but go through the list * anyway */ -if (afu->phb ==NULL ) +if (afu ==NULL || afu->phb ==NULL )return result;list_for_each_entry (afu_dev, &afu->phb->bus->devices, bus_list) {@@ -1832,7 +1832,8 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev, {struct cxl *adapter =pci_get_drvdata (pdev);struct cxl_afu *afu; -pci_ers_result_t result =PCI_ERS_RESULT_NEED_RESET , afu_result; +pci_ers_result_t result =PCI_ERS_RESULT_NEED_RESET ; +pci_ers_result_t afu_result =PCI_ERS_RESULT_NEED_RESET ;int i;/* At this point, we could still have an interrupt pending. @@ -1843,6 +1844,7 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev,/* If we're permanently dead, give up. */ if (state == pci_channel_io_perm_failure) { +spin_lock (&adapter->afu_list_lock);for (i =0 ; i < adapter->slices; i++) { afu = adapter->afu[i];/* @@ -1851,6 +1853,7 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev,*/ cxl_vphb_error_detected (afu, state); } +spin_unlock (&adapter->afu_list_lock);return PCI_ERS_RESULT_DISCONNECT ; }@@ -1932,11 +1935,17 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev,* * In slot_reset, free the old resources and allocate new ones. * * In resume, clear the flag to allow things to start. */ + +/* Make sure no one else changes the afu list */ +spin_lock (&adapter->afu_list_lock); +for (i =0 ; i < adapter->slices; i++) { afu = adapter->afu[i]; - afu_result =cxl_vphb_error_detected (afu, state); +if (afu ==NULL ) +continue ; + afu_result =cxl_vphb_error_detected (afu, state);cxl_context_detach_all (afu); cxl_ops->afu_deactivate_mode (afu, afu->current_mode);pci_deconfigure_afu (afu);@@ -1948,6 +1957,7 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev, (result == PCI_ERS_RESULT_NEED_RESET)) result =PCI_ERS_RESULT_NONE ; } +spin_unlock (&adapter->afu_list_lock);/* should take the context lock here */ if (cxl_adapter_context_lock (adapter) !=0 )@@ -1980,14 +1990,18 @@ static pci_ers_result_t cxl_pci_slot_reset(struct pci_dev *pdev)*/ cxl_adapter_context_unlock (adapter); +spin_lock (&adapter->afu_list_lock);for (i =0 ; i < adapter->slices; i++) { afu = adapter->afu[i]; +if (afu ==NULL ) +continue ; +if (pci_configure_afu (afu, adapter, pdev)) - goto err; + goto err_unlock;if (cxl_afu_select_best_mode (afu)) - goto err; + goto err_unlock;if (afu->phb ==NULL )continue ;@@ -1999,16 +2013,16 @@ static pci_ers_result_t cxl_pci_slot_reset(struct pci_dev *pdev) ctx =cxl_get_context (afu_dev);if (ctx &&cxl_release_context (ctx)) - goto err; + goto err_unlock; ctx =cxl_dev_context_init (afu_dev);if (IS_ERR (ctx)) - goto err; + goto err_unlock; afu_dev->dev.archdata.cxl_ctx = ctx;if (cxl_ops->afu_check_and_enable (afu)) - goto err; + goto err_unlock; afu_dev->error_state = pci_channel_io_normal;@@ -2029,8 +2043,13 @@ static pci_ers_result_t cxl_pci_slot_reset(struct pci_dev *pdev) result =PCI_ERS_RESULT_DISCONNECT ; } } + +spin_unlock (&adapter->afu_list_lock);return result; +err_unlock: +spin_unlock (&adapter->afu_list_lock); + err:/* All the bits that happen in both error_detected and cxl_remove * should be idempotent, so we don't need to worry about leaving a mix @@ -2051,10 +2070,11 @@ static void cxl_pci_resume(struct pci_dev *pdev)* This is not the place to be checking if everything came back up * properly, because there's no return value: do that in slot_reset. */ +spin_lock (&adapter->afu_list_lock);for (i =0 ; i < adapter->slices; i++) { afu = adapter->afu[i]; -if (afu->phb ==NULL ) +if (afu ==NULL || afu->phb ==NULL )continue ;list_for_each_entry (afu_dev, &afu->phb->bus->devices, bus_list) {@@ -2063,6 +2083,7 @@ static void cxl_pci_resume(struct pci_dev *pdev) afu_dev->driver->err_handler->resume (afu_dev); } } +spin_unlock (&adapter->afu_list_lock); }static const struct pci_error_handlers cxl_err_handler = {
Signature · 2 lines
Andrew Donnellan OzLabs, ADL Canberra [email protected] IBM Australia Limited
Quoted 4 lines · Andrew Donnellan
Quoted 1 line · Vaibhav Jain
Within cxl module, iteration over array '
adapter->slices' may be racy
adapter->slicesisn't an array,adapter->afuis the array.
Thanks for catching this. Have fixed the patch description in the resent patch.
Quoted 3 lines
Does this need to go to stable? (I'm guessing we've been hitting actual Oopses?)
Re-send patch marked to stable.
Quoted 1 line
Acked-by Andrew Donnellan <[email protected]>
Thanks !!
Signature · 2 lines
Vaibhav Jain <[email protected]> Linux Technology Center, IBM India Pvt. Ltd.
Le 29/01/2019 à 07:15, Vaibhav Jain a écrit :
Quoted 6 lines
Within cxl module, iteration over array '
adapter->slices' may be racy at few points as it might be simultaneously read during an EEH and its contents being set to NULL while driver is being unloaded or unbound from the adapter. This might result in a NULL pointer to 'struct afu' being de-referenced during an EEH thereby causing a kernel oops.
Quoted 6 lines
This patch fixes this by making sure that all access to the array '
adapter->slices' is wrapped within the context of spin-lock 'adapter->afu_list_lock'.Signed-off-by Vaibhav Jain <[email protected]>---
Thanks for fixing this!
Quoted 180 lines
Changelog:
v3:
* Updated a slice loop incxl_pci_error_detectected()to ignore NULL slices [Fred]
* Added a NULL AFU check incxl_pci_slot_reset()[Fred]v2:
* Fixed a wrong comparison of non-null pointer [Fred]
* Moved a call tocxl_vphb_error_detected()within a branch that checks for not null AFU pointer in 'adapter->slices' [Fred]
* Removed a misleading comment in code.--- drivers/misc/cxl/guest.c | 2 ++ drivers/misc/cxl/pci.c | 39 ++++++++++++++++++++++++++++++--------- 2 files changed, 32 insertions(+), 9 deletions(-)drivers/misc/cxl/guest.c +2
-0@@ -267,6 +267,7 @@ static int guest_reset(struct cxl *adapter)int i, rc;pr_devel ("Adapter reset request\n" ); +spin_lock (&adapter->afu_list_lock);for (i =0 ; i < adapter->slices; i++) {if ((afu = adapter->afu[i])) { pci_error_handlers(afu, CXL_ERROR_DETECTED_EVENT,@@ -283,6 +284,7 @@ static int guest_reset(struct cxl *adapter)pci_error_handlers (afu,CXL_RESUME_EVENT ,0 ); } } +spin_unlock (&adapter->afu_list_lock);return rc; }drivers/misc/cxl/pci.c +30
-9@@ -1805,7 +1805,7 @@ static pci_ers_result_t cxl_vphb_error_detected(struct cxl_afu *afu,/* There should only be one entry, but go through the list * anyway */ -if (afu->phb ==NULL ) +if (afu ==NULL || afu->phb ==NULL )return result;list_for_each_entry (afu_dev, &afu->phb->bus->devices, bus_list) {@@ -1832,7 +1832,8 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev, {struct cxl *adapter =pci_get_drvdata (pdev);struct cxl_afu *afu; -pci_ers_result_t result =PCI_ERS_RESULT_NEED_RESET , afu_result; +pci_ers_result_t result =PCI_ERS_RESULT_NEED_RESET ; +pci_ers_result_t afu_result =PCI_ERS_RESULT_NEED_RESET ;int i;/* At this point, we could still have an interrupt pending. @@ -1843,6 +1844,7 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev,/* If we're permanently dead, give up. */ if (state == pci_channel_io_perm_failure) { +spin_lock (&adapter->afu_list_lock);for (i =0 ; i < adapter->slices; i++) { afu = adapter->afu[i];/* @@ -1851,6 +1853,7 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev,*/ cxl_vphb_error_detected (afu, state); } +spin_unlock (&adapter->afu_list_lock);return PCI_ERS_RESULT_DISCONNECT ; }@@ -1932,11 +1935,17 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev,* * In slot_reset, free the old resources and allocate new ones. * * In resume, clear the flag to allow things to start. */ + +/* Make sure no one else changes the afu list */ +spin_lock (&adapter->afu_list_lock); +for (i =0 ; i < adapter->slices; i++) { afu = adapter->afu[i]; - afu_result =cxl_vphb_error_detected (afu, state); +if (afu ==NULL ) +continue ; + afu_result =cxl_vphb_error_detected (afu, state);cxl_context_detach_all (afu); cxl_ops->afu_deactivate_mode (afu, afu->current_mode);pci_deconfigure_afu (afu);@@ -1948,6 +1957,7 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev, (result == PCI_ERS_RESULT_NEED_RESET)) result =PCI_ERS_RESULT_NONE ; } +spin_unlock (&adapter->afu_list_lock);/* should take the context lock here */ if (cxl_adapter_context_lock (adapter) !=0 )@@ -1980,14 +1990,18 @@ static pci_ers_result_t cxl_pci_slot_reset(struct pci_dev *pdev)*/ cxl_adapter_context_unlock (adapter); +spin_lock (&adapter->afu_list_lock);for (i =0 ; i < adapter->slices; i++) { afu = adapter->afu[i]; +if (afu ==NULL ) +continue ; +if (pci_configure_afu (afu, adapter, pdev)) - goto err; + goto err_unlock;if (cxl_afu_select_best_mode (afu)) - goto err; + goto err_unlock;if (afu->phb ==NULL )continue ;@@ -1999,16 +2013,16 @@ static pci_ers_result_t cxl_pci_slot_reset(struct pci_dev *pdev) ctx =cxl_get_context (afu_dev);if (ctx &&cxl_release_context (ctx)) - goto err; + goto err_unlock; ctx =cxl_dev_context_init (afu_dev);if (IS_ERR (ctx)) - goto err; + goto err_unlock; afu_dev->dev.archdata.cxl_ctx = ctx;if (cxl_ops->afu_check_and_enable (afu)) - goto err; + goto err_unlock; afu_dev->error_state = pci_channel_io_normal;@@ -2029,8 +2043,13 @@ static pci_ers_result_t cxl_pci_slot_reset(struct pci_dev *pdev) result =PCI_ERS_RESULT_DISCONNECT ; } } + +spin_unlock (&adapter->afu_list_lock);return result; +err_unlock: +spin_unlock (&adapter->afu_list_lock); + err:/* All the bits that happen in both error_detected and cxl_remove * should be idempotent, so we don't need to worry about leaving a mix @@ -2051,10 +2070,11 @@ static void cxl_pci_resume(struct pci_dev *pdev)* This is not the place to be checking if everything came back up * properly, because there's no return value: do that in slot_reset. */ +spin_lock (&adapter->afu_list_lock);for (i =0 ; i < adapter->slices; i++) { afu = adapter->afu[i]; -if (afu->phb ==NULL ) +if (afu ==NULL || afu->phb ==NULL )continue ;list_for_each_entry (afu_dev, &afu->phb->bus->devices, bus_list) {@@ -2063,6 +2083,7 @@ static void cxl_pci_resume(struct pci_dev *pdev) afu_dev->driver->err_handler->resume (afu_dev); } } +spin_unlock (&adapter->afu_list_lock); }static const struct pci_error_handlers cxl_err_handler = {
Quoted 19 lines · Vaibhav Jain
Within cxl module, iteration over array '
adapter->slices' may be racy at few points as it might be simultaneously read during an EEH and its contents being set to NULL while driver is being unloaded or unbound from the adapter. This might result in a NULL pointer to 'struct afu' being de-referenced during an EEH thereby causing a kernel oops.This patch fixes this by making sure that all access to the array '
adapter->slices' is wrapped within the context of spin-lock 'adapter->afu_list_lock'.Signed-off-by Vaibhav Jain <[email protected]>---
Changelog:v3:
* Updated a slice loop incxl_pci_error_detectected()to ignore NULL slices [Fred]
* Added a NULL AFU check incxl_pci_slot_reset()[Fred]
Quoted 6 lines
v2:
* Fixed a wrong comparison of non-null pointer [Fred]
* Moved a call tocxl_vphb_error_detected()within a branch that checks for not null AFU pointer in 'adapter->slices' [Fred]
* Removed a misleading comment in code.
---
Thanks